# Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models

arXiv: https://arxiv.org/abs/2410.22660 · HTML: https://mlsanity.com/paper/2410.22660/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 55 references that are in the map.
- First posted on arXiv 30 Oct 2024.

## Builds on (most cited first, 20 of 20)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages](https://mlsanity.com/paper/2104.05596/) (2021)
- [Aya 23: Open Weight Releases to Further Multilingual Progress](https://mlsanity.com/paper/2405.15032/) (2024)
- [GLUECoS : An Evaluation Benchmark for Code-Switched NLP](https://mlsanity.com/paper/2004.12376/) (2020)
- [Syntactic Structure from Deep Learning](https://mlsanity.com/paper/2004.10827/) (2020)
- [LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation](https://mlsanity.com/paper/2005.04322/) (2020)
- [BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance](https://mlsanity.com/paper/1911.02969/) (2019)
- [A Survey of Code-switched Speech and Language Processing](https://mlsanity.com/paper/1904.00784/) (2019)
- [NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages](https://mlsanity.com/paper/2205.15960/) (2022)
- [One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia](https://mlsanity.com/paper/2203.13357/) (2022)
- [Multilingual Large Language Models Are Not (Yet) Code-Switchers](https://mlsanity.com/paper/2305.14235/) (2023)
- [Are Multilingual Models Effective in Code-Switching?](https://mlsanity.com/paper/2103.13309/) (2021)
- [Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences](https://mlsanity.com/paper/1909.08582/) (2019)
- [Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages](https://mlsanity.com/paper/2303.13592/) (2023)
- [WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines](https://mlsanity.com/paper/2410.12705/) (2024)
- [HinGE: A Dataset for Generation and Evaluation of Code-Mixed Hinglish Text](https://mlsanity.com/paper/2107.03760/) (2021)
- [MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences](https://mlsanity.com/paper/2410.02381/) (2024)
- [Grammatical Constraints on Intra-sentential Code-Switching: From Theories to Working Models](https://mlsanity.com/paper/1612.04538/) (2016)
- [Code-Mixed Probes Show How Pre-Trained Models Generalise On Code-Switched Text](https://mlsanity.com/paper/2403.04872/) (2024)

## Built on by (most cited first, 6 of 6)

- [SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset](https://mlsanity.com/paper/2506.00087/) (2025)
- [Can Large Language Models Understand, Reason About, and Generate Code-Switched Text?](https://mlsanity.com/paper/2601.07153/) (2026)
- [Bringing Up a Bilingual BabyLM: Investigating Multilingual Language Acquisition Using Small-Scale Models](https://mlsanity.com/paper/2603.29552/) (2026)
- [SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs](https://mlsanity.com/paper/2507.14894/) (2025)
- [Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switch](https://mlsanity.com/paper/2604.15490/) (2026)
- [Code Mixologist : A Practitioner's Guide to Building Code-Mixed LLMs](https://mlsanity.com/paper/2602.11181/) (2026)

## Abstract (arXiv)

Code-switching, the phenomenon of alternating between two or more languages in a single conversation, presents unique challenges for Natural Language Processing (NLP). Most existing research focuses on either syntactic constraints or neural generation, with few efforts to integrate linguistic theory with large language models (LLMs) for generating natural code-switched text. In this paper, we introduce EZSwitch, a novel framework that combines Equivalence Constraint Theory (ECT) with LLMs to produce linguistically valid and fluent code-switched text. We evaluate our method using both human judgments and automatic metrics, demonstrating a significant improvement in the quality of generated code-switching sentences compared to baseline LLMs. To address the lack of suitable evaluation metrics, we conduct a comprehensive correlation study of various automatic metrics against human scores, revealing that current metrics often fail to capture the nuanced fluency of code-switched text. Additionally, we create CSPref, a human preference dataset based on human ratings and analyze model performance across ``hard`` and ``easy`` examples. Our findings indicate that incorporating linguistic constraints into LLMs leads to more robust and human-aligned generation, paving the way for scalable code-switching text generation across diverse language pairs.